What are the hardware requirements for Code 33B GGUF?

Code 33B GGUF requires approximately 13.5 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Code 33B GGUF and how large is it?

Code 33B GGUF is developed by TheBloke, a model with 33b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

Where can I download or evaluate Code 33B GGUF?

Code 33B GGUF is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Code 33B GGUF by TheBloke — VRAM 13.5GB

Name: Code 33B GGUF
Author: TheBloke

Code 33B GGUF is an open-source language model by TheBloke. Features: 33b LLM, VRAM: 13.5GB, License: cc-by-nc-nd-4.0, Quantized, LLM Explorer Score: 0.1.

Base model:ajibawa-2023/code-3... Base model:quantized:ajibawa-2... Code Dataset:ajibawa-2023/code-74k-... En Gguf Llama Quantized Region:us

Model Card on HF 🤗: https://huggingface.co/TheBloke/Code-33B-GGUF

Code 33B GGUF Parameters and Internals

Model Type

llama

Additional Notes

Code 33B is a Large Language Model good for code generation across various programming languages including Python, Java, JavaScript, GO, C++, and Rust. Detailed explanations are provided along with code.

Supported Languages

en (English)

Training Details

Data Sources:

Python-Code-23k-ShareGPT, Code-74k-ShareGPT

Methodology:

DeepSpeed codebase used for training purpose.

Training Time:

6 days & 5 hours

Hardware Used:

4 x A100 80GB

Input Output

Input Format:

This is a conversation with your helpful AI assistant. AI assistant can generate Code in various Programming Languages along with necessary explanation. Context You are a helpful AI assistant. USER: {prompt} ASSISTANT:

LLM Name	Code 33B GGUF
Repository 🤗	https://huggingface.co/TheBloke/Code-33B-GGUF
Model Name	Code 33B
Model Creator	Feynman Innovations
Base Model(s)	Code 33B ajibawa-2023/Code-33B
Model Size	33b
Required VRAM	13.5 GB
Updated	2026-07-28
Maintainer	TheBloke
Model Type	llama
Model Files	13.5 GB 17.3 GB 15.8 GB 14.1 GB 18.4 GB 19.6 GB 18.4 GB 22.4 GB 23.0 GB 22.4 GB 26.7 GB 34.6 GB
Supported Languages	en
GGUF Quantization	Yes
Quantization Type	gguf
Model Architecture	AutoModel
License	cc-by-nc-nd-4.0

Rank the Code 33B GGUF capabilities

Have you tried this model? Rate its performance — this feedback helps the ML community find the right model for their needs.

Instruction Following and Task Automation
Factuality and Completeness of Knowledge
Censorship and Alignment
Data Analysis and Insight Generation
Text Generation
Text Summarization and Feature Extraction
Code Generation
Multi-Language Support and Translation

Best Alternatives to Code 33B GGUF

Best Alternatives	Context / RAM	Downloads	Likes
...epseek Coder 33B Instruct GGUF	0K / 14 GB	15508	196
WhiteRabbitNeo 33B V1 GGUF	0K / 12.3 GB	2404	34
Everyone Coder 33B Base GGUF	0K / 12.4 GB	728	13
Deepseek Coder 33B Base GGUF	0K / 14 GB	3387	9
WizardCoder 33B V1.1 GGUF	0K / 14 GB	274	45
Python Code 33B GGUF	0K / 13.5 GB	641	3
Vicuna 33B Coder GGUF	0K / 13.5 GB	462	6
Vicuna 33B GGUF	0K / 13.5 GB	719	16
Chronos 33B GGUF	0K / 13.5 GB	486	2
Airoboros 33B 2.1 GGUF	0K / 13.5 GB	690	14

Note: green Score (e.g. "73.2") means that the model is better than TheBloke/Code-33B-GGUF.